Dani
054c0e56e9
Removed the deprecated 'model: sonnet' field from command frontmatter to fix compatibility issues with Claude Code. Commands will now inherit the model from the active conversation instead of using a hardcoded deprecated model identifier. Changes: - Removed 'model: sonnet' from 142 command files across all categories - Commands now use default model inheritance behavior - Preserved 'model: claude-sonnet-4-5-20250929' in gemini-review.md (valid model) - 67 commands without model field remain unchanged This resolves the "model: sonnet not found" error reported in GitHub issues and aligns with Claude Code's recommended practice of letting commands inherit the conversation model. Affected categories: - Database/Supabase commands (8 files) - Documentation commands (8 files) - Deployment commands (11 files) - Setup commands (14 files) - Performance commands (8 files) - Team commands (14 files) - Security commands (6 files) - NextJS/Vercel commands (10 files) - Sync commands (14 files) - And more across other categories 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2.0 KiB
Simulation Calibrator
Calibrate simulation accuracy with comprehensive validation and continuous improvement: $ARGUMENTS
Current Simulation State
- Simulation type: Based on $ARGUMENTS (business, technical, behavioral, strategic simulation)
- Accuracy requirements: Mission-critical (95%+), strategic (80-95%), or exploratory (50-70%)
- Validation data: Historical outcomes, real-world benchmarks, and expert assessments
- Performance metrics: Current accuracy levels and improvement opportunities
Task
Implement systematic simulation calibration with comprehensive accuracy improvement:
Simulation Type: Use $ARGUMENTS to calibrate business simulations, technical models, behavioral predictions, or strategic scenarios
Calibration Framework:
- Baseline Assessment - Historical validation, accuracy metrics, and error pattern analysis
- Bias Detection - Systematic identification of cognitive, data, and model biases with mitigation strategies
- Validation Loops - Multi-level validation with internal consistency, expert review, and empirical testing
- Real-Time Calibration - Continuous monitoring, automated adjustments, and adaptive learning integration
- Quality Assurance - Meta-calibration assessment and improvement sustainability
- Improvement Roadmap - Systematic enhancement strategies with performance tracking
Advanced Features: Automated bias detection, machine learning calibration, cross-simulation learning, and predictive accuracy optimization.
Quality Control: Independent validation, benchmark comparison, and comprehensive documentation for institutional learning.
Output: Calibrated simulation with validated accuracy metrics, bias correction reports, continuous improvement systems, and enhanced decision support reliability.